Research on data correction method of micro air quality detector based on combination of partial least squares and random forest regression

Abstract

The issue of air quality has attracted more and more attention. The main methods for monitoring the concentration of pollutants in the air include national monitoring station monitoring and micro air quality detector testing. Since the electrochemical sensor of the micro air quality detector is susceptible to interference, the monitored data has a certain deviation. In this paper, the combined model of partial least square regression and random forest regression (PLS-RFR) is used to correct the detection data of the micro air quality detector. First, correlation analysis is used to find out the factors that affect the concentration of pollutants. Second, partial least squares regression is used to give the quantitative relationship of the influence of each influencing factor on the concentration of pollutants. Finally, the predicted value of partial least squares regression and various influencing factors are used as independent variables, and the pollutant concentration monitored by the national monitoring station is used as the dependent variable, and the PLS-RFR model is obtained with the help of random forest software package. Relative Mean Absolute Percent Error (MAPE), Mean Absolute Error (MAE), goodness of fit (R2), and Root Mean Square Error (RMSE) are used as evaluation indicators to compare PLS-RFR model, support vector machine model and multilayer perceptron neural network. The results show that no matter which evaluation index, the prediction effect of the PLS-RFR model is the best, and the model has a good prediction effect in the training set or the test set, indicating that the model has good generalization ability. This model can play an active role in the promotion and deployment of micro air quality detectors.

Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination model

“…The pearson correlation coefficient (Eq. ( 1)) is used in this paper to screen the main factors affecting air quality [25,32]. The value range of the pearson correlation coefficient is [-1, 1], and the larger its absolute value, the stronger the correlation between the two variables.…”

“…Although the prediction effect of artificial neural network is good, neural network usually requires more data than traditional machine learning algorithms, and the output results are difficult to interpret. Random forest algorithm [24][25][26] is also commonly used to predict air quality in recent years, but random forest is prone to overfitting in some noisy regression or classification problems. Support Vector Machine (SVM) can cleverly solve small sample, high-dimensional, nonlinear problems, and it follows the principle of structural risk minimization.…”

A method for calibrating measurement data of micro air quality monitor based on MLR-BRT-ARIMA combined model

“…, random forests 28−30 and other machine learning algorithms for air quality forecasting have gradually developed. Liu et al used the partial least squares and random forest combined model to successfully predict the air quality in Nanjing, and used this combined model to calibrate the micro air quality monitor31 . Liu et al added geographic features such as population, land use, economy, pollution sources, and terrain parameters to the time series, and established a framework for forecasting air quality in northern…”